Apihub Mcp Server

Created By
APIHub4 days ago
Discover and call paid APIs with USDC credits. No wallet, no gas, no per-provider SDKs
Overview

APIHub MCP Server

Discover and call paid APIs with USDC credits. No wallet, no gas, no per-provider SDKs.

APIHub is a marketplace of paid APIs accessible through a single MCP server. Pay once with USDC on Base to top up credits, then every API call is a free database debit at the edge — no signing, no gas, no per-request blockchain transaction.

What you can do

  • Discover APIs by capability, category, or price across both APIHub's onboarded catalog and the broader x402 ecosystem
  • Call any onboarded service via apihub_call with full pricing transparency
  • Call external x402 APIs via apihub_call_external — credits cover the on-chain payment so you don't need a wallet
  • Read web content via apihub_read_content, which uses a paid content gateway to fetch and parse pages
  • Top up credits directly from your AI assistant via apihub_topup (returns browser, CLI, and direct x402 payment paths)

Available tools

  • apihub_search — Search APIs by capability, category, or price range
  • apihub_list_services — List all onboarded services
  • apihub_get_service — Fetch full schemas, pricing, and endpoints for a service
  • apihub_call — Make a paid call to an onboarded API
  • apihub_search_external — Search the external x402 catalog
  • apihub_call_external — Call any external x402 URL using your credits
  • apihub_read_content — Read a web page through a paid content gateway
  • apihub_topup — Get payment instructions to add credits
  • apihub_balance — Check current balance and spending history

Quick start

  1. Sign up at apihub.io for a free API key
  2. Add the config to your MCP client (Claude Desktop, Cursor, Codex, Claude Code)
  3. Top up credits with apihub_topup (or use the CLI)
  4. Search and call APIs

Why credits instead of per-call x402

  • Gasless: pay on-chain once when topping up, not per request
  • Walletless: no USDC custody, no EIP-3009 signing, no gas math
  • Works in any MCP client: just a Bearer token in the header
  • Instant: edge-side database debit, no block confirmations per call

Server Config

{
  "mcpServers": {
    "apihub": {
      "url": "https://mcp.apihub.io/mcp",
      "headers": {
        "Authorization": "Bearer ahk_your_api_key"
      }
    }
  }
}
Project Info
Created At
4 days ago
Updated At
4 days ago
Author Name
APIHub
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Scratchpad Mcp
@MikePressure

scratchpad-mcp is an MCP server that gives AI agents persistent, token-efficient storage. It solves a specific waste problem: agents constantly re-read files they've already seen, re-summarize documents they've already processed, and re-load context they've already understood. Every one of those round-trips burns tokens for no new information. This server fixes that with eight tools designed around how agents actually work: Versioned writes. write_file automatically versions every write and keeps the 10 most recent versions per file. Storage is append-only on success and atomic on failure partial writes can't corrupt state. Structured diffs. read_file accepts a since_version parameter and returns a JSON line-diff against that prior version instead of the full content. Agents that have already seen v1 can ask "what changed in v3?" and get a small structured payload they can reason about, not the entire file again. Append-only logs. append_log and read_log give agents an event-stream they can replay. Cursor-based pagination (since_entry + last_entry_id + has_more) means an agent can checkpoint where it left off and resume cheaply. On-demand summaries. summarize_file calls Claude Haiku to summarize files over ~2000 estimated tokens. Summaries are cached per file version, so repeat calls on an unchanged file cost nothing. The threshold is enforced server-side you can't accidentally pay to summarize something small. Per-agent isolation. Every operation is scoped by an agent_id parameter, so one server instance can serve many agents without leaking state between them. Storage limits. 1 MB per file write, 64 KB per log entry, 1000 files / 100k log entries / 100 MB total per agent sane multi-tenant guardrails out of the box. Backed by a single SQLite file (Postgres migration is on the roadmap). All SQL is parameterized, paths are validated against a strict allowlist, and the security model is documented honestly it's safe for one-user-per-process deployments today, and the V2 plan derives agent_id from the caller's API key for true multi-tenancy. Build agents that remember what they've already seen.

12 hours ago